salesforce / BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
BSD 3-Clause "New" or "Revised" License
4.86k stars 648 forks source link

Filter and Captioner #86

Closed baolp closed 2 years ago

baolp commented 2 years ago

Hi, thanks for your outstanding work.

I don't find the usage of Filter and Captioner in blip_pretrain.py.

Do you provide this code?

Thanks

KosukeTrue commented 1 year ago

hello, can you share the details about the code of Filter and Captioner?

LiJunnan1992 commented 1 year ago

Hi, the filter is the retrieval model finetuned on COCO. The captioner is the captioning model finetuned on COCO.

aries-young commented 1 year ago

Hi, the filter is the retrieval model finetuned on COCO. The captioner is the captioning model finetuned on COCO.

Hi, could you please kindly provide the code of the process of Dataset Bootstrapping?